skip to content

Cambridge Centre for Smart Infrastructure and Construction

Transforming infrastructure through smarter information

Following his CSIC workshop held earlier this year and expressed interest from industry partners in forming a special interest group for Computer Vision in construction, Vladimir Vilde, Research Associate at CSIC, considers limitations and opportunities – and invites industry practitioners interested in deploying computer vision-based solutions to join the new group.

Vision is crucial to understanding the space around us, identifying objects and avoiding harm. While eyes provide sight, it is the complex workings of the brain that interpret and understand what we see. In the digital world, Computer Vision (CV) replicates parts of the complex processes of the human vision system to interpret and understand images that provide data and insights.

The full potential for civil infrastructure is underexplored and only a low level of Computer Vision-based technologies are currently in use. Computer Vision provides an adaptable and cost-effective approach and there may be lessons learned from solutions applied to other sectors which can be applied to civil engineering. Vladimir Vilde

CV technologies are more efficient and versatile than ever before. The last decade has marked considerable progress in the capabilities of cameras and computers making CV affordable for a wide range of uses, from families detecting wildlife in their garden, to NASA scientists guiding a robot on Mars.

While CV shows potential to add value in civil engineering applications, there are challenges. The infrastructure and construction sector has not been quick to adopt digitalisation – many processes remain paper-based and data collected from sensors are not always optimised. It remains a siloed and fragmented industry and a digital skills shortage further restricts progress using digital technologies. That said, the adaptability and wide range of applications for CV makes it potentially very well suited to a sector where different structures and sites present challenges for asset managers and developers, such as: identifying people or hazards on a railway line; keeping track of site progress; making sure construction workers operate in a safe environment; supporting autonomous operations; and tracking defects in structures as part of a monitoring system. CV for infrastructure and construction is attracting a number of start-ups developing solutions for the sector. 

The full potential for civil infrastructure is underexplored and only a low level of CV-based technologies are currently in use.  CV provides an adaptable and cost-effective approach and there may be lessons learned from solutions applied to other sectors which can be applied to civil engineering. As a relatively new field of technology within infrastructure and construction, some organisations rely on short term consultancy expertise to develop a CV solution. However, without an adequate understanding of both the opportunities and limitations of these technologies, organisations risk a disappointing return on investment.

‘Computer Vision Beyond Black Boxes’ workshop

Feedback from industry partners to CSIC researchers about experiences applying CV solutions has highlighted results falling short of expectations. My research considers the development of standardised descriptions and explanations of CV technology for the sector in order to: enhance understanding and support use of CV in construction and asset management; identify when use of CV is appropriate; and better manage risk and expectation when planning a new CV approach.

The CSIC virtual workshop ‘Computer Vision Beyond Black Boxes’ was organised in early 2021 for industry partners to increase awareness and provide a realistic understanding of the capabilities of the technology, highlighting a number of approaches for civil infrastructure. The workshop demonstrated, through a number of examples, how fully understanding a problem before matching it to a CV solution yields results. The workshop established that a solution doesn’t need to be expensive or very complex, just thoughtful.

Computer Vision special interest group

Interest in the workshop has led to the formation of a CSIC Computer Vision special interest group with the aim of collaborating to share information and experiences in using the technology to increase knowledge and understanding. Researchers will provide insights to using CV and gather information from industry practitioners about what the real-world need is for CV and why it has not always worked well in the past. The group’s focus will be practical: discussion of technologies and algorithms will also include approaches to implementation, costs and legal considerations surrounding the deployment of CV. If your organisation is interested in joining the CSIC Computer Vision special interest group, please contact the project lead CSIC Research Associate Dr Vladimir Vilde:


• Vladimir Vilde's work is supported by the Centre for Digital Built Britain (CDBB)/the Construction Innovation Hub (CIH) funded by UK Research and Innovation through the Industrial Strategy Fund.